Memòria cau
Estratègies i implementació de memòria cau
background-tasks
Nomik94
백그라운드 작업 패턴 레퍼런스. Use when: 백그라운드 작업, 비동기 작업, Celery, 이메일 발송, 무거운 작업, 큐, task queue, 작업 스케줄링, periodic task, BackgroundTasks, worker, 작업 재시도, retry, dead letter. NOT for: 단순 async/await (FastAPI 기본 비동기).
what-if-analysis
magfrump
Perform a structured prospective consequence analysis of a proposed change — a plan, design, migration, refactor, policy, or any artifact that proposes doing something different from the status quo. This skill systematically explores "what if this assumption is wrong?" and "what would need to be true for this to fail?" It traces second-order effects, maps hidden couplings, and stress-tests the highest-confidence assumptions. Differentiated from critique skills (cowen-critique, yglesias-critique) which evaluate whether an argument is good — this skill evaluates what happens if the argument is wrong, and what the consequences are even if it's right. Use this skill when the user asks things like "what could go wrong with this", "stress-test this plan", "what am I not seeing", "what are the risks", "what are the second-order effects", "what breaks if we're wrong", "what assumptions is this making", or "what if this assumption doesn't hold". Also trigger when the user is about to make a significant, hard-to-reverse change and wants to understand the consequence space before committing, or when invoked as a sub-procedure of divergent-design to stress-test top candidates before a decision is finalized. Distinct from pre-mortem: that skill operates retrospectively (assume failure has already happened → write the narrative of why), while this skill operates prospectively (the plan is on the table → map the consequence space around it). Trigger phrases that name a failure as already having happened — "pre-mortem this", "imagine 6 months later and this failed", "write the failure story", "tell me why this failed" — route to pre-mortem, not here. The two skills compose: run what-if first to map the territory, then pre-mortem to walk the specific failure paths through it. NOTE: This skill can optionally receive upstream reports (fact-check, critique) but does not require them. If critique reports are provided, use them to identify which assumptions the critics didn't examine — that's where this skill adds the most value.
redis
kprsnt2
Redis best practices including data modeling, caching patterns, and performance optimization.
django
kprsnt2
Django framework best practices including project structure, ORM, and security.
escrever-como-antonio
sallzzbr
Use quando o usuário pedir conteúdo na própria voz, na voz de Antonio Salgado ou consistente com um perfil-de-voz.md, com possível calibração para personas locais.
vercel-react-best-practices
Lium-7768
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
prompt-caching
anilsoylu
Guide for optimizing prompt caching in agentic AI applications. Use when building Claude agents, optimizing API costs, designing system prompts, managing tool definitions, implementing compaction, or troubleshooting cache miss rates. Triggers: "prompt caching", "cache hit rate", "reduce API costs", "system prompt ordering", "tool definitions caching", "compaction", "context window management", "agent cost optimization", "prefix caching", "cache-safe forking", "agentic loop cost", "token cost reduction", "cache miss debugging".
backend-architect
shaul1991
Backend Architect Agent. ìì¤í ì¤ê³, ìí¤í ì² ê²°ì , 기ì ì íì ë´ë¹í©ëë¤. ì¤ê³, ìí¤í ì², 구조, í¨í´, 기ì ì í ê´ë ¨ ìì² ì ì¬ì©ë©ëë¤.
analisar-voz
sallzzbr
Use quando o usuário fornecer amostras e quiser extrair ou atualizar um perfil de voz estruturado, inclusive a partir de DOCX, Markdown ou texto.
turborepo
ehyland
Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines, creates packages, sets up monorepo, shares code between apps, runs changed/affected packages, debugs cache, or has apps/packages directories.
symfony-symfony-messenger
data219
Async message handling with Symfony Messenger; configure transports (RabbitMQ, Redis, Doctrine); implement handlers, middleware, and retry strategies
ckvd-fcp-monitor
terrylica
Monitor and diagnose FCP (Failover Control Protocol) behavior, cache health, and data source performance. TRIGGERS - FCP issues, cache problems, slow data, Vision API errors, REST fallback, data source debugging.
cloud-native-engineer
Codewithsaffy
The definitive skill for building and deploying high-performance, distributed systems using Cloud Native standards (Dapr, Redis, Microservices). Use when a project requires professional-grade architecture, cross-service communication, elastic scaling, and sub-second agentic latency. Mandatory for flawless deployments on Kubernetes (Local or Cloud).
analise-de-aula
sallzzbr
"Use para analisar aula, docx e transcrição e diagnosticar adequação pedagógica antes de gerar conteúdo de curso."
security-audit
Nomik94
프로젝트 보안 패턴, JWT 인증, RBAC, 예외 처리 레퍼런스. Use when: 로그인 구현, 인증 구현, JWT 토큰 발급, 액세스 토큰, 리프레시 토큰, Refresh Token Rotation, 토큰 블랙리스트, Redis 토큰 저장소, 권한 관리, RBAC 설정, 역할 기반 접근제어, require_roles, Role vs UserRole, 예외 처리 설계, UnauthorizedException, ForbiddenException, mappings.py, 패스워드 해싱, 비밀번호 암호화, bcrypt, HashedPassword, 보안 점검, 보안 체크리스트, 취약점 확인, OWASP, 코드 감사, CORS 설정, rate limiting, 에러 응답에 민감정보 노출. NOT for: 일반적인 HTTP 상태코드 의미, OAuth2 프로바이더 연동.
media-storage
dev-goraebap
"파일 업로드·저장소·첨부 관리 패턴. Actions: 파일 업로드, 이미지 업로드, 파일 처리, 저장소 연동, 썸네일 첨부, 색상 추출, file upload, image upload, storage, attachment, thumbnail. Patterns: Active Storage, blobs 테이블, attachments 테이블, 다형적 첨부, 중복 파일 감지. Storage: Cloudflare R2, AWS S3, @aws-sdk/client-s3, UUID key, 2-level 디렉토리, CDN URL, presigned URL. DB: Drizzle ORM, blob, checksum, MD5, metadata JSON, MIME, byte_size. Color: 지배적 색상 추출, dominant color, Gemini API, hex, blobs.metadata. Query: 썸네일 조회, 서브쿼리, leftJoin, view-model, CDN URL 변환. Stack: SvelteKit, +server.ts, TypeScript."
mech-interp
Pranav-Karra-3301
Mechanistic interpretability skill for understanding neural network internals. Use when: (1) Working with TransformerLens, nnsight, or SAELens (2) Analyzing attention patterns, circuits, or features (3) Training or analyzing sparse autoencoders (SAEs) (4) Activation patching, logit lens, or direct logit attribution (5) Understanding model internals ("what is this head doing?") (6) Setting up a mech interp research project Triggers: "mech interp", "mechanistic interpretability", "TransformerLens", "SAE", "sparse autoencoder", "activation patching", "logit lens", "circuits", "features", "attention heads", "residual stream", "nnsight", "nnterp", "superposition", "polysemantic", "monosemantic", "ablation", "probing", "induction head"
sintese-semanal
sallzzbr
"Use para fechar briefing semanal de ads e selecionar três ações por impacto a partir de análises existentes."
env-file-generator
ehtbanton
Generate properly structured .env environment files with common variables, documentation comments, and secure placeholder patterns. Triggers on "create .env file", "generate environment variables", "env file for", "dotenv template".
oh-my-opencode-update
canyangliunian
Use when upgrading, reinstalling, or troubleshooting the oh-my-opencode plugin, especially when old caches, lockfiles, or permissions prevent the new version from taking effect.
redis
acejou27
Redis in-memory data structure store - use for caching, session management, pub/sub, real-time analytics, and key-value storage
react-nextjs
Alicoder001
Next.js 14+ App Router best practices including Server Components, data fetching, caching, and Vercel optimization patterns. Use for Next.js development with waterfall prevention, bundle optimization, and server actions.
auditoria-de-estrutura
sallzzbr
"Use para avaliar estrutura de conta de anúncios, campanhas, públicos, posicionamentos e diversidade criativa."
nchan-expert
tailuge
Expert guidance for Nchan, a scalable pub/sub server for Nginx. Use this skill when you need to configure Nchan endpoints (publisher/subscriber), set up horizontal scaling with Redis, implement security patterns (authorization, X-Accel-Redirect), or troubleshoot Nchan performance and metrics.